Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to news articles and information sources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.69
    ä¹
    -0.68
    ciating
    -0.68
    ombat
    -0.67
    eer
    -0.64
    UFC
    -0.61
    ulla
    -0.60
    feeding
    -0.60
    feat
    -0.60
    rament
    -0.59
    POSITIVE LOGITS
     suspic
    0.84
     Ahead
    0.81
    ahead
    0.76
    uez
    0.75
     aft
    0.72
     ahead
    0.71
     forward
    0.68
    ãĤ¤ãĥĪ
    0.67
     Glass
    0.66
    ression
    0.65
    Act Density 0.025%

    No Known Activations